Computer system for displaying the logistical path of entities over time

Abstract

A computer system displays paths based on processing of at least one series of input data including a list of time-stamped tasks. The tasks include an identifier of an object, an identifier of an action and a piece of time information. The system includes a piece of connected user computer equipment executing a display application and at least one remote server executing an application for calculating a path model from tables.

1 . A computer system for displaying paths based on processing of at least one series of input data comprising:
 a list of time-stamped tasks comprising an identifier of an object, an identifier of an action and a piece of time information   a piece of connected “user” computer equipment executing a display application;   at least one remote server executing an application for calculating a path model from tables;   an administration server managing a plurality of user accounts and recording, in each user's account, the tables originating from the user as well as data relating to a specific configuration of the user and a result of the processing carried out on a shared calculation server;   at least one shared calculation server comprising a GPU graphics processor executing a deep learning application from data associated with a user and building a digital model subsequently recorded in the user's account on at least one of the administration or calculation servers;   the user equipment executing an application controlling the calculation, on one of the calculation servers, of an analytical or predictive state for the retrieval and display of data corresponding to the result of this calculation on the interface of the user equipment.   
     
     
         2 . The computer system according to  claim 1 , further comprising at least one CPU server distributing the calculation load between a plurality of shared calculation servers. 
     
     
         3 . The computer system according to  claim 1 , further comprising anonymising the identifiers of the objects and/or the identifiers of the actions of each user, and a recorder converting the anonymised data in an encrypted form on the user's account, the data processed by the calculation server(s) exclusively consisting of anonymised data. 
     
     
         4 . The computer system according to the preceding  claim 3 , wherein the encryption is carried out using a hash function. 
     
     
         5 . An automatic method for displaying paths from the processing of at least one series of input data comprising a list of time-stamped tasks comprising an identifier of an object, the identifier of an action and a piece of time information, comprising:
 executing on a server of an application for calculating a path model from tables;   executing on a piece of connected “user” computer equipment of an application for controlling a calculation, on one of the calculation servers of an analytical or predictive state for retrieval and display of the data corresponding to the result of this calculation on the interface of the user equipment and of a display application;   executing on an administration server of an application for managing a plurality of user accounts and for recording, in each user's account, the tables originating from the user as well as data relating to a specific configuration of the user and the result of the processing carried out on a shared calculation server; and   executing on at least one shared calculation server comprising a GPU graphics processor of an application for deep learning from data associated with a user, and for constructing a digital model subsequently recorded in the user's account on at least one of the administration or calculation servers.   
     
     
         6 . The automatic method for displaying paths according to  claim 5 , further comprising determining a digital model predictive of an evolution of an order preparation process, comprising:
 calculating, for each of the future orders (C 1 (P j , T)), the time t of passage of each of the orders Ci  at each of the P j  order picking stations of a logistics warehouse;   then calculating, for each of the time slots At x  and for each of the stations P j , the number N x  of orders C i ;   applying a Petri nets model to all the stations P j , each of the orders C i  being represented by a digital token JN i , according to injection hypotheses of the tokens and the model representing the processing carried out for the preparation of the orders; and   then implementing a “linear hybrid automaton” system to determine the parameters of predictive digital model representative of a future state of the order processing chain.   
     
     
         7 . The automatic method for displaying paths according to  claim 6 , wherein the display application controls the dynamic display of the evolution of the tokens according to the predictive digital model. 
     
     
         8 . The automatic method for displaying paths according to  claim 6 , further comprising determining at least one parameter of the order preparation process.